Models

DeepSeek V4 Flash Vision Exp (batch)

deepseek ↗ · 1049K ctx · 8 providers · updated 2026-09-12 06:15 UTC

Cheapest
$0.165 via OpenRouter
Avg price
$0.544 /1M
providers
8
Tokens (24h)
68B
Volume (24h)
$11.2K est.
(3 × $0.110 + $0.330) ÷ 4 = $0.165/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.110, 3:1 $0.165, 1:1 $0.220, output only $0.330 per 1M.

The board shows this model's cheapest measured offer ($0.165/1M); the smaller figure under it is the mean of the 10 offers listed below ($0.544/1M). Add those up and divide — it matches. 24h token volume (68B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.110$0.330 API-measured
fireworks_ai Pricebook (LiteLLM) $0.220$0.660 Official list
openrouter Pricebook (LiteLLM) $0.220$0.660 Official list
requesty Requesty $0.220$0.660 API-measured
deepinfra HuggingFace Router $0.440$1.32 268ms 146 API-measured
deepseek Pricebook (LiteLLM) $0.440$1.32 Official list
novita Pricebook (LiteLLM) $0.440$1.32 Official list
novita HuggingFace Router $0.440$1.32 596ms 127 API-measured
novita-ai Novita AI $0.440$1.32 API-measured
0g-teetls 0G Router $0.660$1.98 API-measured

Volume trend

88B 20d d-19 · 29B tokensd-18 · 0 tokensd-17 · 33B tokensd-16 · 33B tokensd-15 · 32B tokensd-14 · 30B tokensd-13 · 25B tokensd-12 · 27B tokensd-11 · 34B tokensd-10 · 46B tokensd-9 · 79B tokensd-8 · 69B tokensd-7 · 75B tokensd-6 · 67B tokensd-5 · 85B tokensd-4 · 88B tokensd-3 · 81B tokensd-2 · 80B tokensd-1 · 76B tokensd-0 · 68B tokens

Last 20 days: 29B → 68B (+132%); range 0–88B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/deepseek-v4-flash-vision-exp.json. Free reuse requires attribution to tkx.org.

FAQ

How much does DeepSeek V4 Flash Vision Exp (batch) cost?

Cheapest measured offer right now: $0.11/1M input, $0.33/1M output via openrouter-best — across 8 tracked providers, refreshed hourly.

Who serves DeepSeek V4 Flash Vision Exp (batch)?

8 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is DeepSeek V4 Flash Vision Exp (batch) used?

DeepSeek V4 Flash Vision Exp (batch) routed 68B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings